Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered; the description adds real value beyond that by disclosing the output verdict vocabulary, the fact that reset windows and reasons come back, and the important caveat that task size is a labeled heuristic because vendors don't publish per-task usage. It stops short of describing cost, latency, or what happens when plans are omitted/invalid.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The first sentence front-loads the decision context and return contract, which is the right structure. The 23-id plan enumeration is bulky and could be delegated to list_plans/get_tool_plans, but it does carry genuine signal because the schema provides no enum for 'plan'.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, and the description covers what comes back (verdict, plan, reasons, reset windows) closely enough for an agent to act on it. Combined with the read-only annotation and explicit heuristic caveat, nothing essential for calling or interpreting the tool is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With only 50% schema coverage, the description compensates well: it defines the size labels (small/medium/large) with concrete examples, states the acceptable plan ids explicitly since the schema leaves 'plan' as an unconstrained string, and clarifies the 'current' parameter as the plan in use now. The 'task' parameter is left unexplained in both schema and description, which is the remaining gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

A specific verb-and-resource statement with the decision context ('for agents deciding whether to start a task') and a concrete return contract: verdict go | wait | switch, a recommended plan, reasons and reset windows. It is clearly distinguishable from siblings like route_task and pick_plan because it frames the question as affordability rather than routing or selection.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The opening clause gives a clear when-to-use context: an agent about to start a task with a known plan set and estimated size. However, it does not explicitly say when to use route_task or pick_plan instead, even though it notes it 'reuses the route_task logic' - that is a relationship hint, not a routing rule.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.